Subquestions

Which country has the highest and lowest score for the six factors

GDP Per Captia

hap_df |>
  mutate(country = fct_reorder(country, gdp_per_capita))|>
  plot_ly (
  x = ~country, y = ~gdp_per_capita, color = ~year,
  type = "bar", colors = "viridis") |>
  layout(
    title = "GDP Per Capita",
    xaxis = list(
      title = "country",
      tickfont = list(size = 6)
      ),
    yaxis = list(title = "GDP Per Capita"),
    autosize = F, width = 1000, height = 500
  )

## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()

Social Support

hap_df |>
  mutate(country = fct_reorder(country, social_support))|>
  plot_ly (
  x = ~country, y = ~social_support, color = ~year,
  type = "bar", colors = "viridis") |>
  layout(
    title = "Social Support/Having Someone to Count On In Time of Trouble",
    xaxis = list(
      title = "country",
      tickfont = list(size = 6)
      ),
    yaxis = list(title = "Score"),
    autosize = F, width = 1000, height = 500
  )

## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()

life Expectancy

hap_df |>
  mutate(country = fct_reorder(country, health_life_expectancy))|>
  plot_ly (
  x = ~country, y = ~health_life_expectancy, color = ~year,
  type = "bar", colors = "viridis") |>
  layout(
    title = "Healthy Life Expectancy",
    xaxis = list(
      title = "country",
      tickfont = list(size = 6)
      ),
    yaxis = list(title = "Score"),
    autosize = F, width = 1000, height = 500
  )

## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()

Freedom to make Choice

hap_df |>
  mutate(
    country = fct_reorder(country, freedom_to_make_life_choices))|>
  plot_ly (
  x = ~country, y = ~freedom_to_make_life_choices, color = ~year,
  type = "bar", colors = "viridis") |>
  layout(
    title = "Freedom to Make Life Choices",
    xaxis = list(
      title = "country",
      tickfont = list(size = 6)
      ),
    yaxis = list(title = "Score"),
    autosize = F, width = 1000, height = 500
  )

## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()

Perception of Corruption

hap_df |>
  mutate(country = fct_reorder(country, perception_of_corruption))|>
  plot_ly (
  x = ~country, y = ~perception_of_corruption, color = ~year,
  type = "bar", colors = "viridis") |>
  layout(
    title = "Perception of Corruption",
    xaxis = list(
      title = "country",
      tickfont = list(size = 6)
      ),
    yaxis = list(title = "Score"),
    autosize = F, width = 1000, height = 500
  )

## Warning: There was 1 warning in `mutate()`.
## ℹ In argument: `country = fct_reorder(country, perception_of_corruption)`.
## Caused by warning:
## ! `fct_reorder()` removing 1 missing value.
## ℹ Use `.na_rm = TRUE` to silence this message.
## ℹ Use `.na_rm = FALSE` to preserve NAs.

## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()

## Warning: Ignoring 1 observations

Generosity

hap_df |>
  mutate(country = fct_reorder(country, generosity))|>
  plot_ly (
  x = ~country, y = ~generosity, color = ~year,
  type = "bar", colors = "viridis") |>
  layout(
    title = "Genersoity",
    xaxis = list(
      title = "country",
      tickfont = list(size = 6)
      ),
    yaxis = list(title = "Score"),
    autosize = F, width = 1000, height = 500
  )

## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()

Iteration

factor_country_level <- function(data, variable, title) {
  p = data %>%
    mutate(country = fct_reorder(country, .data[[variable]])) %>%
    plot_ly(
      x = ~country, 
      y = as.formula(paste0("~", variable)), 
      color = ~year,
      type = 'bar', 
      colors = 'viridis'
    ) %>%
    layout(
      title = title,
      xaxis = list(title = "Country", tickfont = list(size = 6)),
      yaxis = list(title = "Score"),
      autosize = F, width = 1000, height = 500
    )
  
  print(p)
}

# Create a list of variables and corresponding titles
variables_and_titles <- list(
  list(variable = "gdp_per_capita", title = "GDP Per Capita"),
  list(variable = "social_support", title = "Social Support/Having Someone to Count On In Time of Trouble"),
  list(variable = "health_life_expectancy", title = "Healthy Life Expectancy"),
  list(variable = "freedom_to_make_life_choices", title = "Freedom to Make Life Choices"),
  list(variable = "perception_of_corruption", title = "Perception of Corruption"),
  list(variable = "generosity", title = "Generosity")
)

# Use map to create a list of plots
plots <- map(variables_and_titles, ~factor_country_level(hap_df, .x$variable, .x$title))

for (plot in plots) {
  print(plot)
}

World Trends of the Six Happiness Indicators from 2015 to 2019

hap_df |>
  group_by(year) |>
  summarise(
    average_gdp_per_capita = mean(gdp_per_capita, na.rm = TRUE),
    average_social_support = mean(social_support, na.rm = TRUE),
    average_healthy_life_expectancy = mean(health_life_expectancy, na.rm = TRUE),
    average_freedom_to_make_life_choices = mean(freedom_to_make_life_choices, na.rm = TRUE),
    average_perception_of_corruption = mean(perception_of_corruption, na.rm = TRUE),
    average_generosity = mean(generosity, na.rm = TRUE)
  )|>
  pivot_longer(
    average_gdp_per_capita:average_generosity,
    names_to ="factor",
    names_prefix = "average_",
    values_to = "average_score"
  )|>
  plot_ly(
    x = ~year, y = ~average_score, color = ~factor,
    type = "scatter", mode = "lines+markers", colors = "viridis") |>
  layout(
    title = "World Trends of Happiness Indicators from 2015 to 2019",
    xaxis = list( title = "Year"),
    yaxis = list(title = "Average Score"),
    autosize = F, width = 1000, height = 500
  )

## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()

Which region has the highest and lowest score for the six factors

GDP Per Capita

hap_df |>
  mutate(region = fct_reorder(region, gdp_per_capita))|>
  group_by(region, year)|>
  summarise(
    average_gdp_per_capita = mean(gdp_per_capita, na.rm = TRUE)
  ) |>
  plot_ly (
  x = ~region, y = ~average_gdp_per_capita, color = ~year,
  type = "bar", colors = "viridis") |>
  layout(
    title = "GDP Per Capita By Region",
    xaxis = list(title = "Region"),
    yaxis = list(title = "Average Score"),
    autosize = F, width = 1000, height = 500
  )

## `summarise()` has grouped output by 'region'. You can override using the
## `.groups` argument.

## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()

Regional Trend

regional_hap_df |>
  filter(factor == "gdp_per_capita")|>
  plot_ly(
      x = ~year, y = ~average_score, color = ~region,
      mode = 'lines+markers', type = 'scatter', colors = 'viridis',
      name = ~region) |>
    layout(
      title = paste("Regional Trend for GDP Per Captia from 2015 to 2019"),
      xaxis = list(title = "Year"),
      yaxis = list(title = "Average Score"),
      autosize = F, width = 1000, height = 500
    )

## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()

Social Support

hap_df |>
  mutate(region = fct_reorder(region, social_support))|>
  group_by(region, year)|>
  summarise(
    average_social_support = mean(social_support, na.rm = TRUE)
  ) |>
  plot_ly (
  x = ~region, y = ~average_social_support, color = ~year,
  type = "bar", colors = "viridis") |>
  layout(
    title = "Social Support By Region",
    xaxis = list(title = "Region"),
    yaxis = list(title = "Average Score"),
    autosize = F, width = 1000, height = 500
  )

## `summarise()` has grouped output by 'region'. You can override using the
## `.groups` argument.

## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()

Regional Trend

regional_hap_df |>
  filter(factor == "social_support")|>
  plot_ly(
      x = ~year, y = ~average_score, color = ~region,
      mode = 'lines+markers', type = 'scatter', colors = 'viridis',
      name = ~region) |>
    layout(
      title = paste("Regional Trend for Social Support from 2015 to 2019"),
      xaxis = list(title = "Year"),
      yaxis = list(title = "Average Score"),
      autosize = F, width = 1000, height = 500
    )

## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()

Life Expectancy

hap_df |>
  mutate(region = fct_reorder(region, health_life_expectancy))|>
  group_by(region, year)|>
  summarise(
    average_life_expectancy = mean(health_life_expectancy, na.rm = TRUE)
  ) |>
  plot_ly (
  x = ~region, y = ~average_life_expectancy, color = ~year,
  type = "bar", colors = "viridis") |>
  layout(
    title = "Healthy Life Expectancy By Region",
    xaxis = list(title = "Region"),
    yaxis = list(title = "Average Score"),
    autosize = F, width = 1000, height = 500
  )

## `summarise()` has grouped output by 'region'. You can override using the
## `.groups` argument.

## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()

Regional Trend

regional_hap_df |>
  filter(factor == "healthy_life_expectancy")|>
  plot_ly(
      x = ~year, y = ~average_score, color = ~region,
      mode = 'lines+markers', type = 'scatter', colors = 'viridis',
      name = ~region) |>
    layout(
      title = paste("Regional Trend for Life Expectancy from 2015 to 2019"),
      xaxis = list(title = "Year"),
      yaxis = list(title = "Average Score"),
      autosize = F, width = 1000, height = 500
    )

## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()

Freedom to Make Choice

hap_df |>
  mutate(region = fct_reorder(region, freedom_to_make_life_choices))|>
  group_by(region, year)|>
  summarise(
    average_freedom = mean(freedom_to_make_life_choices, na.rm = TRUE)
  ) |>
  plot_ly (
  x = ~region, y = ~average_freedom, color = ~year,
  type = "bar", colors = "viridis") |>
  layout(
    title = "Freedom to Make Choice By Region",
    xaxis = list(title = "Region"),
    yaxis = list(title = "Average Score"),
    autosize = F, width = 1000, height = 500
  )

## `summarise()` has grouped output by 'region'. You can override using the
## `.groups` argument.

## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()

Regional Trend

regional_hap_df |>
  filter(factor == "freedom_to_make_life_choices")|>
  plot_ly(
      x = ~year, y = ~average_score, color = ~region,
      mode = 'lines+markers', type = 'scatter', colors = 'viridis',
      name = ~region) |>
    layout(
      title = paste("Regional Trend for Freedom to Make Life Choices from 2015 to 2019"),
      xaxis = list(title = "Year"),
      yaxis = list(title = "Average Score"),
      autosize = F, width = 1000, height = 500
    )

## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()

Perception of Corruption

hap_df |>
  mutate(region = fct_reorder(region, perception_of_corruption))|>
  group_by(region, year)|>
  summarise(
    average_corruption = mean(perception_of_corruption, na.rm = TRUE)
  ) |>
  plot_ly (
  x = ~region, y = ~average_corruption, color = ~year,
  type = "bar", colors = "viridis") |>
  layout(
    title = "Perception of Corruption By Region",
    xaxis = list(title = "Region"),
    yaxis = list(title = "Average Score"),
    autosize = F, width = 1000, height = 500
  )

## Warning: There was 1 warning in `mutate()`.
## ℹ In argument: `region = fct_reorder(region, perception_of_corruption)`.
## Caused by warning:
## ! `fct_reorder()` removing 1 missing value.
## ℹ Use `.na_rm = TRUE` to silence this message.
## ℹ Use `.na_rm = FALSE` to preserve NAs.

## `summarise()` has grouped output by 'region'. You can override using the
## `.groups` argument.

## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()

Regional Trend

regional_hap_df |>
  filter(factor == "perception_of_corruption")|>
  plot_ly(
      x = ~year, y = ~average_score, color = ~region,
      mode = 'lines+markers', type = 'scatter', colors = 'viridis',
      name = ~region) |>
    layout(
      title = paste("Regional Trend for Perception of Corruption from 2015 to 2019"),
      xaxis = list(title = "Year"),
      yaxis = list(title = "Average Score"),
      autosize = F, width = 1000, height = 500
    )

## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()

Generosity

hap_df |>
  mutate(region = fct_reorder(region, generosity))|>
  group_by(region, year)|>
  summarise(
    average_generosity = mean(generosity, na.rm = TRUE)
  ) |>
  plot_ly (
  x = ~region, y = ~average_generosity, color = ~year,
  type = "bar", colors = "viridis") |>
  layout(
    title = "Generosity By Region",
    xaxis = list(title = "Region"),
    yaxis = list(title = "Average Score"),
    autosize = F, width = 1000, height = 500
  )

## `summarise()` has grouped output by 'region'. You can override using the
## `.groups` argument.

## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()

Regional Trend

regional_hap_df |>
  filter(factor == "generosity")|>
  plot_ly(
      x = ~year, y = ~average_score, color = ~region,
      mode = 'lines+markers', type = 'scatter', colors = 'viridis',
      name = ~region) |>
    layout(
      title = paste("Regional Trend for Generosity from 2015 to 2019"),
      xaxis = list(title = "Year"),
      yaxis = list(title = "Average Score"),
      autosize = F, width = 1000, height = 500
    )

## Warning: Specifying width/height in layout() is now deprecated.
## Please specify in ggplotly() or plot_ly()

World Map

library(ggplot2)
library(stringr)
library(maps)

## 
## Attaching package: 'maps'

## The following object is masked from 'package:purrr':
## 
##     map

library(magrittr)

## 
## Attaching package: 'magrittr'

## The following object is masked from 'package:purrr':
## 
##     set_names

## The following object is masked from 'package:tidyr':
## 
##     extract

library(rvest)

## 
## Attaching package: 'rvest'

## The following object is masked from 'package:readr':
## 
##     guess_encoding

library(countrycode)

iso_codes = countrycode::codelist[, c("un.name.en", "iso3c")]
names(iso_codes) = c("Country", "ISO3")

world_data <- ggplot2::map_data('world')
world_data <- fortify(world_data)

hap_df['ISO3'] <- iso_codes$ISO3[match(hap_df$country, iso_codes$Country)]
world_data["ISO3"] <- iso_codes$ISO3[match(world_data$region, iso_codes$Country)]

hap_df = hap_df |>
  mutate(
    ISO3 = if_else(country == "United States", "USA", ISO3),
    ISO3 = if_else(country == "United Kingdom", "GBR", ISO3),
    ISO3 = if_else(country == "Venezuela", "VEN", ISO3),
    ISO3 = if_else(country == "Czech Republic", "CZE", ISO3),
    ISO3 = if_else(country == "Taiwan", "TWN", ISO3),
    ISO3 = if_else(country == "South Korea", "KOR", ISO3),
    ISO3 = if_else(country == "Bolivia", "BOL", ISO3),
    ISO3 = if_else(country == "Moldova", "MDA", ISO3),
    ISO3 = if_else(country == "Russia", "RUS", ISO3),
    ISO3 = if_else(country == "Hong Kong", "CHN", ISO3),
    ISO3 = if_else(country == "Vietnam", "VNM", ISO3),
    ISO3 = if_else(country == "Turkey", "TUR", ISO3),
    ISO3 = if_else(country == "Macedonia", "MKD", ISO3),
    ISO3 = if_else(country == "Laos", "LAO", ISO3),
    ISO3 = if_else(country == "Swaziland", "SWZ", ISO3),
    ISO3 = if_else(country == "Palestinian Territories", "PSE", ISO3),
    ISO3 = if_else(country == "Iran", "IRN", ISO3),
    ISO3 = if_else(country == "Congo (Kinshasa)", "COD", ISO3),
    ISO3 = if_else(country == "Congo (Brazzaville)", "COG", ISO3),
    ISO3 = if_else(country == "Tanzania", "TZA", ISO3),
    ISO3 = if_else(country == "Syria", "SYR", ISO3),
    ISO3 = if_else(country == "Puerto Rico", "PRI", ISO3)
  )|>
  mutate(country = recode(str_trim(country),
                         "United States" = "USA",
                         "United Kingdom" = "UK",
                         "Congo (Kinshasa)" = "Democratic Republic of the Congo",
                         "Congo (Brazzaville)" = "Republic of Congo"))

world_data = world_data|>
  mutate(country = region)|>
  select(-region)

worldjoin <- inner_join(world_data, hap_df, by = "country")

## Warning in inner_join(world_data, hap_df, by = "country"): Detected an unexpected many-to-many relationship between `x` and `y`.
## ℹ Row 11 of `x` matches multiple rows in `y`.
## ℹ Row 153 of `y` matches multiple rows in `x`.
## ℹ If a many-to-many relationship is expected, set `relationship =
##   "many-to-many"` to silence this warning.

## compile all map theme configurations
cleanup <- theme(
  axis.text = element_blank(),
  axis.line = element_blank(),
  axis.ticks = element_blank(),
  panel.border = element_blank(),
  panel.grid = element_blank(),
  axis.title = element_blank(),
  panel.background = element_rect(fill = "white"),
  plot.title = element_text(hjust = 0.5)
)

## plot our merged data

gdp <- worldjoin %>% 
  ggplot(mapping = aes(
    x=long,
    y=lat,
    group=group)) +
  scale_fill_viridis_c(option = "C") +
  coord_fixed(1.3) +
  geom_polygon(aes(fill=gdp_per_capita)) +
  ggtitle("GDP Per Capita") +
  cleanup

gdp